onboarding-designer
Skill7 starsChanged 43 days agoMITView on GitHub
Design the first-run experience for mobile apps: value discovery, registration strategy, permission sequencing, empty states, and day 1-3 retention hooks. Use when the user is building or improving onboarding, sign-up flow, permission prompts, or early retention.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- sohaibdevv/Claude-Agentic-Skills2.0-versiontheir own version, first seen Jun 9, 2026
- vignesh2027/Claude-Agentic-Skills2.0-versiontheir own version, first seen May 20, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- vignesh2027/Claude-Agentic-Skills2.0-version★ 6same name
- sohaibdevv/Claude-Agentic-Skills2.0-version★ 2same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository83 other files it gives its agents.
- AGENTS.mdAGENTS.md
- accessibility-enforcerSkill
- access-policy-designerSkill
- adaptive-guardSkill
- agent-reviewerSkill
- anti-ai-slop-designSkill
- api-mock-designerSkill
- api-observability-plannerSkill
- app-store-reviewerSkill
- ask-first-act-laterSkill
- assumption-checkerSkill
- auth-flow-designerSkill
- b2b-founder-roadmapSkill
- brand-name-labSkill
- breaking-change-detectorSkill
- changelog-generatorSkill
- checkpoint-guardianSkill
- claude-style-codingSkill
- claw-integration-designSkill
- context-compressorSkill
- contract-first-designerSkill
- coolify-orchestratorSkill
- crash-analystSkill
- data-lineage-tracerSkill
- data-maskerSkill
- deep-link-architectSkill
- design-intelligenceSkill
- design-md-enforcerSkill
- ecosystem-apiSkill
- ecosystem-databaseSkill
- ecosystem-mobileSkill
- ecosystem-orchestrationSkill
- ecosystem-productSkill
- ecosystem-reasoningSkill
- ecosystem-securitySkill
- ecosystem-webSkill
- error-recoverySkill
- fth-design-crafterSkill
- geo-auditorSkill
- geo-optimizerSkill
- index-advisorSkill
- jev-orchestratorSkill
- mastermind-loggerSkill
- memory-ledgerSkill
- migration-strategistSkill
- mobile-perf-auditorSkill
- mobile-security-auditorSkill
- multi-brain-debateSkill
- multi-brain-expertsSkill
- multi-brain-scoreSkill
- multi-brainSkill
- offline-sync-designerSkill
- output-criticSkill
- parallel-plannerSkill
- pgbouncer-architectSkill
- plan-hardenerSkill
- plan-implement-verify-recoverSkill
- proje-analizcisiSkill
- project-analyzerSkill
- project-focus-firstSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 32
Instead of a stationary 4-page swipe carousel that no one reads, design progressive disclosure.
- Distinctive: line 34
Use tooltip overlays or guided tours only when the user touches a relevant feature.
- Distinctive: line 37
Never trigger the OS-level permission dialog blindly.
- Distinctive: line 39
If they say "No" to the soft prompt, you save the real OS prompt for later.
- Distinctive: line 40
If they say "Yes", you trigger the OS prompt, and they are primed to accept.
- Distinctive: line 92
App Tracking Transparency (ATT): If they use ads, remind them that the ATT prompt must be shown, but should ideally be preceded by a soft …
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Onboarding Designer Protocol
You only get one chance to make a first impression. If a user downloads an app and is immediately hit with 3 native permission dialogs (Push, Location, Tracking) before they even know what the app does, they will delete it. This skill designs onboarding flows optimized for user retention and permission acceptance.
Core principle: Show value before asking for trust.
Workflow
1. Map the required app permissions and account creation needs
2. Design the "Aha!" Moment (Value Proposition)
3. Sequence the Soft & Hard Permission Prompts
4. Design the Empty States (Day 0)
5. Plan the Day 1 to Day 3 Retention HooksStep 1: Requirements Mapping
What does the app absolutely need to function?
- Authentication: Is an account required immediately, or can they browse as a guest? (Apple mandates guest mode if account isn't strictly necessary).
- Permissions: Location, Notifications, Camera, Photo Library, App Tracking Transparency (ATT).
Step 2: Value Discovery
Instead of a stationary 4-page swipe carousel that no one reads, design progressive disclosure.
- Drop the user into the app as quickly as possible.
- Use tooltip overlays or guided tours only when the user touches a relevant feature.
Step 3: Permission Sequencing (The Double-Opt-In)
Never trigger the OS-level permission dialog blindly.
- The "Soft Prompt": A custom UI screen explaining why you need the permission. (e.g., "We need your location to find nearby restaurants.")
- If they say "No" to the soft prompt, you save the real OS prompt for later.
- If they say "Yes", you trigger the OS prompt, and they are primed to accept.
Step 4: Empty States
The moment after onboarding, the app is usually empty (no friends, no data, no history).
- Do not show a blank screen.
- Provide a clear, single Call-To-Action (CTA) pointing to the core value loop (e.g., "Add your first task", "Import your contacts").
Step 5: Retention Hooks
Design the communication strategy to bring them back.
- Day 1: Did they complete the core action? If not, send a helpful local notification or email.
- Day 3: Introduce a power-user feature they haven't discovered yet.
Output Format
# 🚀 Onboarding & First-Run Experience Plan
## 🎯 The "Aha!" Moment
**Goal:** [What is the first thing the user should achieve to feel the app's value?]
**Time to Value:** [e.g., Under 60 seconds]
## 🚦 Registration Strategy
- **Flow:** [e.g., Deferred Login. Let users browse nearby restaurants without an account. Only ask for login when they click 'Order'.]
## 🔐 Permission Sequencing (Double Opt-In)
| Permission | When to Ask (Soft Prompt) | Rationale User Copy |
|---|---|---|
| Location (When In Use) | Upon tapping "Find near me" | "We need your location to show restaurants in your zip code." |
| Push Notifications | After placing the very first order | "Want to know when your food arrives? Enable notifications." |
## 🪹 Empty State Design
**Screen:** [e.g., 'My Orders' Tab]
**Visual:** [Illustration of an empty shopping bag]
**Text:** "You haven't ordered anything yet. Hungry?"
**Action (CTA):** [Button: "Browse Popular Places"]
## 🪝 Day 1-3 Retention Loop
- **Day 1 Trigger:** [If user generated an order: Do nothing. If not: "Still deciding? Here is a $5 promo code."]
- **Day 3 Trigger:** ["Did you know you can save your favorite meals for 1-tap ordering?"]When to Skip
- The user is asking about the visual UI design (colors, corner radius). This is a UX flow and behavioral design skill.
Guardrails
- Apple Guideline 5.1.1 (v): Explicitly warn developers that Apple requires apps to provide "Sign in with Apple" if they use third-party social logins.
- App Tracking Transparency (ATT): If they use ads, remind them that the ATT prompt must be shown, but should ideally be preceded by a soft prompt explaining that tracking keeps the app free.
References
See references/EXAMPLES.md for a worked case.
🔗 Next Steps & Handoffs
<!-- BEGIN GENERATED: handoffs (generated from the ecosystem workflow map by build_ecosystems.py — do not edit by hand) -->Ecosystem: @ecosystem-mobile — Mobile App Domain.
Workflows:
- Feature Architecture Flow (
mobile-feature-architecture, step 4 of 4): last step → once it passes, complete the workflow and report the outcome.
Handoff contract: pass results to the next skill through an inline Handoff block in your reply with the fields skill, workflow, created_at, inputs, summary, and next (the handoff contract of @ecosystem-mobile). If a next skill is not installed, continue with its step from the ecosystem map, or install it with npx skills add fatih-developer/fth-skills --skill <name> after the user agrees.
<!-- END GENERATED: handoffs -->Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

